Blog from November, 2020

Christopher Jason

Clinicians are more likely to schedule a telehealth follow-up if they have immediate access to patient data.

Clinicians with access to a shared inpatient-outpatient EHR were more likely to schedule a telehealth follow-up appointment or conduct laboratory monitoring, rather than an in-person visit, according to a study published in the American Journal of Managed Care.

Additionally, enhanced interoperability and patient data exchange can boost follow-up care efficiency.

“For the growing number of patients with chronic conditions, care transitions, such as those after hospital discharge, require coordination among multiple clinicians practicing in different settings,” the researchers explained.

Seamless data exchange and interoperability are important for making that level of care coordination and follow-up care happen, but for many outpatient clinicians that’s not always the case. Outpatient clinicians do not always have real-time access to patient data from recent hospitalizations.

Researchers studied over 240,000 hospital discharges in patients with diabetes to examine the rates of outpatient follow-up visits, telemedicine, laboratory tests, and readmissions – which provide real-time access to all patient data across both types of care settings – impacted the type of follow-up care following hospital discharge.

Clinicians with a shared inpatient-outpatient EHR were significantly more likely to schedule both telehealth and outpatient laboratory tests, rather than in-person visits. Clinicians using an outpatient-only EHR scheduled follow-up care at a rate of 22.9 percent. That rate increased to 27 percent after clinicians received access to the shared inpatient-outpatient EHR. But there was little correlation between readmissions or 30-day return emergency department visits.

With researchers finding lower rates of follow-up visits and little association between hospital readmissions, researchers said these findings could shift follow-up care delivery without impacting patient care.

“Although EHR interoperability and HIE functionality have been consistently promoted as policy priorities for improving the quality and efficiency of the American health care system, there is still limited research evidence to inform policy makers about the effects of continuity in provider access to patient information,” wrote the study authors.

The researchers also said the study shows the importance of patient data access across a number of providers between facilities.

“Our findings from patients with diabetes also complement findings of previous studies in the same integrated delivery system, in patients with diabetes and in general patient populations, in which both providers and patients reported that EHR use facilitated care coordination both by providing informational continuity among providers and by supporting direct communication between clinicians and medical staff through electronic messaging tools,” explained the study authors.

While some studies showed in-person visits resulted in better patient outcomes, researchers said there was little evidence of worse outcomes in this study. Furthermore, researchers said patient data access may have decreased unnecessary or duplicate testing.  

Although health information exchange is not perfected across health systems, this study shows the importance of patient data exchange.

“Our study finds that movement toward more seamless health information access, even within an already integrated system, can affect the efficiency of follow-up care after hospital discharge without adversely affecting quality,” researchers wrote.

“These shifts may also potentially improve patient convenience through telemedicine follow-up without requiring the transportation and cost of making an in-person visit to health care providers.”

While telehealth is more convenient for patients, it is also beneficial for the current need for social distancing to mitigate the spread of COVID-19.

“Overall, in a setting that implemented a shared EHR with seamless HIE between inpatient and outpatient providers, patient follow-up care after hospital discharge was less likely to include an in-person office visit and instead was managed through exchange of asynchronous secure messages, telephone telemedicine, and outpatient laboratory tests,” concluded the researchers.

Mike Miliard

Researchers say the new tools, developed using EHR data from the pandemic's first wave, can forecast short- and medium-term risks for patients over the course of their hospitalizations.

Researchers at Mount Sinai in New York see promise in new machine learning models they've developed that can assess – within key windows of time – the risk of certain adverse clinical events in some COVID-19 patients.

Research published earlier this month in the Journal of Medical Internet Research describes how the algorithms are enabling better insights into potential risks for a diverse group of COVID-19 patients.

Researchers at Mount Sinai's Icahn School of Medicine and Hasso Plattner Institute for Digital Health gathered electronic health record data from more than 4,000 adult patients admitted to five Mount Sinai Health System hospitals from this spring, during the pandemic's first wave.

Clinicians from the Mount Sinai Covid Informatics Center analyzed characteristics of COVID-19 patients – looking at past medical history, comorbidities, vitals and labs – to help predict the risk of mortality, or critical events such as the need for intubation, within clinically relevant time windows.

By predicting risks for time windows of three, five, seven and 10 days from admission, Mount Sinai researchers say the models offer valuable insights to forecast short and medium-term care decisions for COVID-19 patients over the course of their hospitalizations.

For instance, they note that at the one-week mark – the time period that offered the most accurate prediction of critical events while returning the fewest false positives – conditions such acute kidney injury, fast breathing, high blood sugar and elevated lactate dehydrogenase (indicating tissue damage or disease) were the strongest drivers in predicting critical illness.

Older age, blood level imbalance, and C-reactive protein levels indicating inflammation, were the strongest drivers in predicting mortality.

Some experts have made the case that artificial intelligence had a somewhat disappointing showing in the early days of the pandemic's spread. And it's true that bias in certain algorithms might have an adverse effect on some healthcare disparities.

But AI and machine learning have a big role to play in diagnosis and decision support as the COVID-19 emergency reaches its newest peak. So far, an array of promising models, many pushed out to clinicians via EHR updates, have emerged to help detect the disease and assess risk on a population level.

Mount Sinai, in particular, has been innovating its research into COVID-19 over the eight months since it was inundated with patients during the pandemic's early peak. It's created an AI model to diagnose COVID-19 in patients with otherwise normal lung scans, for instance. And has also pioneered the use of Apple Watch to study COVID-19 stress and burnout among healthcare workers.

"From the initial outburst of COVID-19 in New York City, we saw that COVID-19 presentation and disease course are heterogeneous, and we have built machine learning models using patient data to predict outcomes," said Benjamin Glicksberg, assistant professor of genetics and genomic sciences at the Icahn School of Medicine at Mount Sinai, in a statement.

"Now in the early stages of a second wave, we are much better prepared than before," he said. "We are currently assessing how these models can aid clinical practitioners in managing care of their patients in practice."

Added Dr. Girish Nadkarni, assistant professor of medicine in the nephrology department at the Icahn School: "More importantly, we have created a method that identifies important health markers that drive likelihood estimates for acute care prognosis and can be used by health institutions across the world to improve care decisions, at both the physician and hospital level, and more effectively manage patients with COVID-19."

Kat Jercich

As COVID-19 surges and supply lines become critical, health system leaders are working toward real-time visibility and predictive tools for inventory, pricing, lead times and demand trends.

With the next wave of the COVID-19 pandemic beginning to crash down in hospitals around the country, it's more important than ever for health systems to be well attuned to their supply chain needs.

One of the biggest challenges of the first wave this past spring, of course, was the shortage of personal protective equipment, ventilators and sometimes critical medications. Supply chain vulnerabilities were acute – and that's not counting the ongoing cyberattacks targeted at health system supply lines.

Some of these challenges have been ironed out over the past eight months. But as the COVID-19 crisis surges again, CIOs and other IT professionals say robust supply chains are more important than ever.

As Hal Wolf, CEO of HIMSS (parent company of Healthcare IT News) said this past week, a revolution in supply chain management is long overdue.

"We have really under-focused on supply chain," said Wolf, who noted the critical need to track the source of medications and equipment; understand the quality of materials (being able to discern, for instance, that a shipment of N95 masks is really what it says it is); and ensuring supply chains are not interrupted – all while having visibility into price, inventory control and more.

Hospital leaders around the country told Healthcare IT News that the current segmentation of systems has led to shortages right when facilities needed resources most. 

Models such as CISOM, developed to improve quality and safety through the integration of supply chain and clinical data in healthcare organizations, can address such inefficiencies. But what are some ways that technology might play a role in making supply chain management a more seamless experience? 

Chief information officers and other healthcare leaders who oversee the supply chains weighed in with their own experiences.

"At LifeBridge Health, we have approached the pandemic with a threefold supply strategy: Conserve; source; and, where needed, manufacture," said Tressa Springmann, CIO at LifeBridge Health in Baltimore. "Clearly, as we are now seeing cases rise again, a keen ability to pivot more quickly has surfaced, and a few additional tools would put us into an even better position both now and into the future.

"First, more complete analytics: analytics that tie [predictions of] patient volume and acuity with supply demand would be helpful," she said. 

"Second, real-time artificial intelligence that makes visible the entire life cycle – end-to-end if you will – of the global supply chain. This visibility would enable a more effective response to market disruption, risk reduction and position us more effectively for enhanced business continuity."

"The healthcare industry would tremendously benefit from supply chain IT systems being much more seamlessly integrated with electronic medical records and their respective materials data sets integrated side-by-side with clinical data," said Aaron Miri, chief information officer at Dell Medical School and UT Health in Austin, Texas.

"The current state of this system's bifurcation led us down some rabbit holes during the PPE crunch, during the COVID-19 pandemic, and therefore causes data analytics teams to have to jump over hurdles that shouldn't be this difficult," said Miri.

"Further, it's holding back advancement in value-based care bundles and new VBC products that could be put to market, as looking at a patient's complete health often includes materials and respective pricing of materials used during surgery, recovery and ongoing therapy," he said.

Some health system leaders pointed to technologies such as artificial intelligence and machine learning as ways to help augment inventory control.

"We at Stanford Children's Health would like to see our supply chain tool provide real-time visibility and predictive analysis, such as available inventory, preferential pricing, lead times from different suppliers and demand trending," said Garima Srivastava, executive director of enterprise business systems.

"We would also want a system that can be scaled to incorporate new robotic process automation, artificial intelligence and radio frequency identification-based management," Srivastava added. "These are important for us to move towards the digital transformation and automate lots of manual work, which our supply chain department currently does. It will speed up some processes and will reduce manual errors."

Using RFID in particular, Srivastava pointed out, "we will be able to track high-cost items and can manage our inventory better." 

"We would love to see predictive forecasting and scenario planning, powered by machine learning and AI capabilities, integrated into our demand planning and supply modeling tools," agreed B.J. Moore, CIO at Providence in Renton, Washington. 

"Think about the ability to predict consumption of PPE items based on real-time COVID modeling, patient admissions, and/or case data, and not on historical consumption alone," he mused.

St. Jude Children's Research Hospital CIO Keith Perry also prioritized location awareness. He said he'd like "to have the ability to track an item throughout the supply chain, including (and most important) the 'last mile,' until it physically arrives at the final delivery destination.

"Unlocking or exposing supply-chain data as appropriate for the person who is ordering equipment" would help with efficiency at St. Jude, Perry continued. "That person is the ultimate customer of any supply-chain process."

Bill Donato, vice president of supply chain at the Hospital for Special Surgery in New York City, noted the importance of visibility. 

"One of the critical tools to manage the current and future healthcare supply chain is our ability to monitor in 'real time' the status of our critical suppliers' products from their manufacturing plants through their distribution networks," he said. "Additional transparency of our suppliers' sales and operating plans would allow us to anticipate and more effectively manage disruptions to our supply chain."

Leaders pointed out that the changes implemented in response to COVID-19 would have lasting positive effects. 

"The most pressing need currently which has been highlighted by the supply chain challenges presented by the pandemic is the need for an affordable, efficient and comprehensive, enterprise-wide inventory management system," said Larry Fogarty, vice president of supply chain management at Memphis-based Methodist Le Bonheur Healthcare. 

"This would create coordinated visibility into the availability, stocking profiles and near-expired product monitoring for supply areas across the organization. It would also go a long way in anticipating supply chain exposures, rather than simply reacting to them – a must in the post pandemic world," Fogarty continued.

"Finally, a coordinated system-wide inventory-management system would facilitate timely, inter-facility transfers to best allocate products where and when needed," Fogarty said.

"As the COVID-19 pandemic continues to disrupt the supply chain, globally and at our five-hospital health system, I would love to see a warehouse-management-support system that could better manage, move and track inventory."

Brian Murray, assistant vice president for supply chain procurement at NorthShore University HealthSystem, said, "Business intelligence software that automatically produces executive-level reporting and can help better forecast our need for gowns, gloves, N95s, isolation masks, thermometers and other PPE would be great.

"We are currently opening an offsite warehouse for our system and need a software program that will help us respond to and support COVID-19 needs," he said.

Tanya Townsend, CIO for LCMC Health in New Orleans, said that her system is already taking steps to improve resource management.

"We are embarking on a new enterprise resource planning implementation which will include new Supply Chain functionality. I look forward to having more complete visibility to trace products and how that impacts patient care," said Townsend.

"I'm also excited about a more automated end-to-end process for managing inventory and procuring products," Townsend continued.

Similarly, Suzzanne Thomson Quintero, chief supply chain officer at Orlando Health, said the system has taken advantage of existing capabilities.     

"Orlando Health is fortunate to have its own 90,000 sq. foot distribution center. This distribution hub uses a warehouse management system to forecast product needs for our 15 hospitals," Quintero explained. 

"We recently enhanced the system to provide meaningful reporting to our hospital operators. In addition, we are introducing artificial intelligence into our purchasing operations to help purchase the right product, at the right price, from the right vendor," she said. 

"Also, we are actively exploring robotic process automation to further streamline our operations and meet the needs of our community."

"Advanced inventory-demand planning, modeling and reporting would be a critical functionality to have in our tool kit to drive value in the supply chain, both long-term and during these unprecedented times," said Bill Moir, vice president of supply chain operations at Advocate Aurora Health in Wisconsin and Illinois.

"AAH is committed to enhancing our supply chain to ensure it is a strategic differentiator for our organization," said Moir. "Investments in our infrastructure, like enterprise resource planning, will ensure a strong standardized foundation that we can continue to build upon and innovate from for years to come."

Christopher Jason

The integration of customized EHR templates is one way EHR optimization to reduce clinician burden for allergists.

Further EHR optimization, the integration of EHR scribes, and implementation of clinical decision support (CDS) and computerized physician order entry (CPOE) systems could boost patient care and reduce clinician burden for allergists, according to an article published in Current Allergy and Asthma Reports.

The constant evolution of health IT in the allergy field has impacted allergist workflow. Like most other clinicians, allergists have seen an increase in after-hours workload doing non-clinical jobs such as EHR documentation.

Clinical EHR documentation was initially designed to record clinical information as provider notes in real-time during a consultation, assessment, or treatment, to share patient data between health providers.

While the transition from paper to EHR documentation has allowed for more accessible and legible notes, it is a primary cause of clinician burden due to information overload and larger amounts of text that is not always relevant to patient care.

“Allergists need to find ways to lower this burden in order to continue to provide exceptional evidence-based medical care while minimizing physician burnout,” wrote Annette F. Carlisle, Saul M. Greenbaum, and Mike S. Tankersley, three faculty members at University of Tennessee Health Science Center.

To enhance EHR documentation, AI voice-recognition scribes have started to replace human scribes in the workplace. The authors noted long-term cost savings, decreased training time, and constant availability as benefits of the technology.

While a well-designed EHR scribe possesses the ability to decrease clinician burnout and technology costs, it cannot replicate all benefits that a human scribe brings to a medical office. 

Human scribes can adapt to the process of training, certifying, and managing medical scribes, described the authors. Also, some health systems may have different documentation styles or expectations that cannot be followed by a digital scribe.

Next, digital scribes are not capable of interacting with the provider, other members of the care team, and patients. Because the digital scribe cannot be more than a silent transcriptionist, a health system may have to hire an assistant to fulfill the other tasks of the human scribe.

While the decision of human scribe versus digital scribe is up to the provider, some providers are moving forward with digital scribes to reduce clinician burden.

Along with improving EHR documentation, the three healthcare professionals recommend the implementation of CDS and CPOE systems.

CDS tools enable prescribers to access real-time patient data, ideally resulting in enhanced patient safety, improved compliance rates, and increased medication accuracy. CDS also alerts prescribers to potential errors and adverse drug events.

According to the authors, CPOE integrated reduces medication errors by more than 55 percent. With both CPOE and CDS, medication errors decreased by 83 percent.  

Another way to decrease burden is to enhance EHR usability through EHR optimization.

The authors recommended customized EHR templates that clinicians can easily utilize to view patient medical history. For an allergist, the customized interface would include a history of illnesses, such as asthma, dermatitis, rhinitis, urticarial, food, or venom reactions.

Other allergy-based templates and EHR optimizations include recording allergy skin testing, immunotherapy dose customization, integrating the asthma control test, and incorporation of extract ordering.

Additional templates also include the ability to integrate a template for e-prescribing, office visits, patient portal messaging, and other methods of communication.

Easy access to view and utilize this information would boost patient care and decrease clinician burden.

“The practicing allergist can implement various additional strategies in their office workflow to maximize and synthesize good medicine and good business,” concluded the authors. “Optimal use of office staff, electronic health records, and various workflow efficiencies has been shown to improve job satisfaction and reduce physician burnout.”

David Raths

Study will assess care model that seeks to motivate primary care patients who are dependent on opioids and also have depression

Opioid use and depression frequently occur simultaneously and reinforce each other. Motivating individuals with opioid use disorder and depression to seek and continue treatments has been an unmet challenge for the healthcare system. The Indiana University School of Medicine and Regenstrief Institute faculty have been awarded $3.9 million over four years to collaborate with Kaiser Permanente Washington Health Research Institute scientists on a trial to optimize treatment for opioid use disorder.

The researchers will test whether a scalable, telehealth-delivered collaborative care model can motivate primary care patients who are dependent on opioids and also have depression to increase engagement in evidence-based treatments for pain and opioid-use disorder, while simultaneously improving depression symptoms.

The trial, MI-CARE (short for More Individualized Care: Assessment and Recovery through Engagement), is supported by the National Institute of Health’s (NIH) National Institute of Mental Health, through the Helping to End Addiction Long-term, or NIH HEAL Initiative, to address the national opioid crisis.

“A patient coming into the doctor’s office with a heart problem typically doesn’t have to be motivated to follow a treatment regimen, but for mental health issues, in part because of stigma associated with these disorders, patients often need support to become engaged and motivated to adhere to medications and other recommendations from their primary care physician,” explained Regenstrief Institute Research Scientist and IU  School of Medicine Chancellor’s Professor of Medicine Kurt Kroenke, M.D., co-principal investigator for the Indiana site, in a statement. “In studies that we have conducted and in real world situations during the COVID-19 pandemic, telehealth has shown real potential in supporting patients and families. The MI-CARE trial will evaluate telehealth’s value, coupled with collaborative care, in the fight against opioid use.”

The Indiana site of the randomized, controlled MI-CARE trial will evaluate 400 individuals with opioid dependence and depression. Half will receive usual care from their primary care physicians. The other 200 will be contacted by phone by a behavioral health care nurse and offered the opportunity to receive a nurse-supported telehealth program in collaboration with their primary care team. This will typically include evidence-based medications for opioid use disorder such as buprenorphine or long-acting naltrexone along with treatment aimed at improving their depression.

Outcomes for both the treatment and usual care groups will be determined from the patients’ electronic medical records, which will include clinical, laboratory and other information.

Among its goals, the MI-CARE trial is designed to determine if the promises of telehealth and coordinated care can help primary care physicians provide the care that opioid users with depression so clearly need.